llm-bedrock-mistral

Plugin for LLM adding support for Mistral models in Amazon Bedrock

Installation

Install this plugin in the same environment as LLM. From the current directory

llm install llm-bedrock-mistral

You will need to specify AWS Configuration with the normal boto3 and environment variables.

For example, to use the region us-east-1 and AWS credentials under the personal profile, set the environment variables

export AWS_DEFAULT_REGION=us-east-1
export AWS_PROFILE=personal

This plugin adds model called bedrock-mistral-7b-instruct and bedrock-mixtral-8x7b-instruct. You can also use it with the alias bm7 or bm8.

You can query them like this:

llm -m bedrock-mistral-7b-instruct "Ten great names for a new space station"

llm -m bm7 "Ten great names for a new space station"

You can also chat with the model:

llm chat -m bm8

-o max_tokens, Specify the maximum number of tokens to use in the generated response.
-o temperature, Controls the randomness of predictions made by the model.
-o top_p, Controls the diversity of text that the model generates by setting the percentage.
-o top_k, Controls the number of most-likely candidates that the model considers for the next token.

Use like this:

llm -m bm7 -o max_tokens 20 -o temperature 0 "Return the alphabet. Be succinct."
 Here is the alphabet in English: A, B, C, D, E, F,